Deep Co-occurrence Feature Learning for Visual Object Recognition

Co-occurrence of deep convolutional features for image search

“…Yang et al [18] call it "Spatial co-occurrence Kernel" and considered it as a count of the times that two visual features satisfy a spatial condition. Shih et al [10] present a new idea behind the co-occurrence representation, recording the spatial correlation c between a pair of feature maps k and w, seeking the maximal correlation response for a set of spatial offsets…”

“…Moreover, this high dimensionality makes it unaffordable in deep tensors like VGG with 512 channels. For this reason, Shih et al [10] add a 1 × 1 × N convolution filter to reduce the number of channels before the co-occurrence layer. As a side effect this channel reduction causes a reduction of performance as demonstrated in [10]; this representation was also used in [19].…”

“…Shih et al [10] define co-occurrences as the maximal correlation between a pair of feature maps, for a set of spatial offsets, whilst we define co-occurrences as the sum of the activations inside a region, being the activations value above a threshold. (Section 3.1).…”

“…In order to compare these two different interpretations, we have modified Shih et al [10] method to return a co-occurrence tensor instead of a cooccurrences vector. This modification consists in picking the summed maxi- with the same size than the original activation tensor A as in our method.…”

“…A Co-occurrence matrix [9] is defined from an image being the distribution of co-occurring pixel values at a given spatial offset. Recently, this concept of co-occurrence has been extended to the co-occurrence of features activations in convolutional layers [10]. In this approach, said co-occurrence layer calculates the correlation between each pair of feature maps by means of the maximum product of the activations given a set of spatial offsets.…”